Neo4j----在数据库中更新数据

1、在现有节点中创建关系

from py2neo import NodeSelector,Graph,Node,Relationship
graph = Graph('http://127.0.0.1:7474/db/data')
tx = graph.begin()
selector = NodeSelector(graph)
node_cache = {}

with open("file","r") as relations:
    for line in relations:
        line_split=line.split(";")

        # Check if we have this node in the cache
        if line_split[0] in node_cache:
            node1 = node_cache[line_split[0]]
        else:
            # Query and store for later
            node1 = selector.select("Node",unique_name=line_split[0]).first()
            node_cache[line_split[0]] = node1

        if line_split[1] in node_cache:
            node2 = node_cache[line_split[1]]
        else:
            node2 = selector.select("Node",unique_name=line_split[1]).first()
            node_cache[line_split[1]] = node2

        rs = Relationship(node1,"Relates to",node2)
        tx.create(rs)

tx.commit()

2、在现有图数据库中添加节点和关系

查询数据库中的节点

# 用find_one()方法进行node查找，返回的是查找node的第一个node
data1 = graph.find_one(label='Person', property_key='name', property_value="Alice")

# 用find()方法进行node查找,需要遍历输出
data2 = graph.find(label='PersonTest')

matcher = NodeMatcher(graph)
print(matcher.match('subject').where('_.name='+"'"+s+"'").first())
#(_157:subject {name: 'Georgia'})

#若在数据库中找到节点则不创建新的节点，否则创建新的节点
if len(data2)>0:
    pass
else:
    graph.create(node)

关系查询

match(nodes=None, r_type=None, **properties)

relationship = graph.match_one(r_type='know')
# 若要新增的节点已存在，则判断关系。若新关系与现有关系不同，则添加关系。

mma = RelationshipMatcher(graph)
print(mma.match(r_type="'" + df_data['relation'][m] + "'").first())
#单条关系查询，效果与上面一样，命名已经创建了，但是返回都是None
rel = graph.match_one(r_type="'" + df_data['relation'][m] + "'")
print(rel)

#换种写法就好了
rel = graph.match_one(r_type='contains')
print(rel)
print(mma.match(r_type='contains').first())

# 是我多加了单引号，这下正常了
for m in range(len(df_data)):
    print(df_data['relation'][m])
    # rel = graph.match_one(r_type='contains')
    # print(rel)
    print(mma.match(r_type=df_data['relation'][m]).first())

思路：
1、要先将triple_result.json三元组处理成df_data，之后在创建关系时要用到对应位置的subject和object

2、构建neo4j语义网络的程序

import json
import pandas as pd
from py2neo import Graph,Node,Relationship,NodeMatcher
graph = Graph("http://localhost:7474", username="neo4j", password="neoj4")

graph.delete_all()
matcher = NodeMatcher(graph)


'''
node1 = Node('animal',name = 'cat')
r1 = Relationship(node2,'has',node1)
graph.create(node1)
'''


def data():
    # 去重之后的  665
    triplea = []
    # 去重之前的 1591
    datas = json.load(open('test_triples.json'))
    for data in datas:
        for triples in data['triple_list']:
            if triples in triplea:
                pass
            else:
                triplea.append(triples)

    links_dict = {}
    subject_list = []
    relation_list = []
    object_list = []

    for s, r, o in triplea:
        subject_list.append(s)
        relation_list.append(r)
        object_list.append(o)

        # print(len(subject_list)) #665
    # print(len(relation_list))#665
    # print(len(object_list)) #665
    subject_list = [str(i) for i in subject_list]
    relation_list = [str(i) for i in relation_list]
    object_list = [str(i) for i in object_list]

    # 将提取的三元组信息存到字典中，构成dataframe
    links_dict['subject'] = subject_list
    links_dict['relation'] = relation_list
    links_dict['object'] = object_list
    df_data = pd.DataFrame(links_dict)
    # print(df_data)

    # 只有结点需要去重
    node_sub_key = list(set(subject_list))
    node_obj_key = list(set(object_list))

    return node_sub_key, node_obj_key, df_data

def create_node(nodes,nodeo):
    for name in nodes:
        s_node = Node('subject',name=name)
        graph.create(s_node)
    for name in nodeo:
        o_node = Node('object',name=name)
        graph.create(o_node)

def create_relation(df_data):

    for m in range(0,len(df_data)):
        try:

            rel = Relationship(matcher.match('subject').where("_.name="+"'"+df_data['subject'][m]+"'").first(),
                               df_data['relation'][m],
                               matcher.match('object').where("_.name="+"'"+df_data['object'][m]+"'").first())
            print('创建第%d个关系'%(m))
            graph.create(rel)
        except AttributeError as e:
            print(e,m)

来源：

图挖掘算法总结：https://blog.csdn.net/siwangtt/article/details/109231135